davidgut1982/lore-mcp
by Various
Advanced MCP server for unified knowledge management with PostgreSQL+pgvector, knowledge graphs, research workflows, and Claude Code integration
MCP
davidgut1982/lore-mcp
Added 7 June 2026
Overview
An open-source MCP server that unifies knowledge management using PostgreSQL with pgvector for vector storage, knowledge graphs, and research workflows. It integrates with Claude Code to provide context-aware assistance during development sessions.
Best for
Best for
Developers using Claude Code who want a centralized, searchable knowledge base with vector and graph capabilities
Use cases
- Store and query project documentation with semantic search
- Manage research notes with vector similarity and graph relationships
- Inject relevant context into Claude Code conversations
How to use
Install
pip install lore-knowledge-mcp[semantic] Tools exposed
LORE_SEMANTIC_SEARCHLORE_SEARCH_MODE_DEFAULTLORE_EMBEDDING_MODELLORE_RRF_Kkb_addkb_searchkb_getkb_get_batchkb_listkb_updatekb_deletekb_backfill_embeddingskb_embedding_statusinvestigation_addinvestigation_listinvestigation_getinvestigation_log_experimentinvestigation_list_experimentsinvestigation_delete_noteinvestigation_delete_experiment
Tested with
Claude Desktop, Claude Code
Notes
An open-source MCP server that unifies knowledge management using PostgreSQL with pgvector for vector storage, knowledge graphs, and research workflows. It integrates with Claude Code to provide context-aware assistance during development sessions.
2 stars on GitHub. Last updated 2026-06-02. Licensed MIT.
Use cases
- Store and query project documentation with semantic search
- Manage research notes with vector similarity and graph relationships
- Inject relevant context into Claude Code conversations
Pros
- Combines vector search, graph storage, and research workflows in one server
- Leverages PostgreSQL and pgvector for scalable, well-supported infrastructure
- Open-source Python implementation that is extensible and auditable
Cons
- Requires separate PostgreSQL instance with pgvector extension
- Low GitHub stars suggest limited community adoption and potential instability
- Tightly coupled to Claude Code; may not work as smoothly with other MCP clients
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Combines vector search, graph storage, and research workflows in one server
- Leverages PostgreSQL and pgvector for scalable, well-supported infrastructure
- Open-source Python implementation that is extensible and auditable
Cons
- Requires separate PostgreSQL instance with pgvector extension
- Low GitHub stars suggest limited community adoption and potential instability
- Tightly coupled to Claude Code; may not work as smoothly with other MCP clients
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
